Dataset · lmg-anon
Japanese visual novel translation LLM leaderboard
lmg-anon/vntl-leaderboard
Evaluation results of Japanese-to-English visual novel translation quality for various language models.
What's inside
A small tabular-text set of fewer than 1000 records in English and Japanese, representing the VNTL leaderboard. It compiles preliminary performance scores of various LLMs and traditional machine translation systems in localizing Japanese visual novels into English. The file storage format is not specified in the card.
What you can do with it
- Selecting the best open or commercial LLM for literary translation from Japanese
- Comparing neural network translation quality with traditional translators
- Analyzing model progress in conveying style and dialogue context
- Tasks
- Translation
- Languages
- English, Japanese
- Size
- up to 1K rows
- Downloads this month
- 715
- Likes
- 44
How to load it
from datasets import load_dataset
ds = load_dataset("lmg-anon/vntl-leaderboard")